update docs

Author: jahvon

README.md

@@ -43,6 +43,7 @@ flow complements existing CLI tools by adding multi-project organization, built-
 - **Flexible execution** - Serial, parallel, conditional, and interactive workflows
 - **Workflow generation** - Create projects and workflows from reusable templates
 - **Composable workflows** - Reference and chain workflows within and across projects
+- **Platform integrations** - GitHub Actions, AI assistants (MCP), and more
 
 <p align="center"><img src="docs/_media/demo.gif" alt="flow" width="1600"/></p>
 

docs/README.md

@@ -26,6 +26,7 @@ and cross-project composition. Go beyond task running to workflow management tha
 - **Cross-Project Composition**: Reference and share workflows between different projects
 - **Visual Workflow Browser**: Discover and run workflows with powerful filtering and search
 - **Flexible Configuration**: YAML-based definitions with arguments, secrets, and conditional logic
+- **Platform Integrations**: GitHub Actions, AI assistants (MCP), and more
 
 **Ready to organize your automation?** → [Install flow](installation.md) → [Quick start guide](quickstart.md)
 

docs/guide/integrations.md

@@ -1,8 +1,49 @@
 # Integrations
 
-flow integrates with popular CI/CD platforms and containerized environments to bring your automation anywhere.
+flow integrates with popular CI/CD platforms, AI assistants, and containerized environments to bring your automation anywhere.
 
-## GitHub Actions
+
+## AI Assistant Integration
+
+### Model Context Protocol (MCP) <!-- {docsify-ignore} -->
+
+Connect flow to AI assistants through the local Model Context Protocol server for natural language workflow management.
+The flow MCP server enables AI assistants to discover, understand, and execute your flow workflows through conversational interfaces.
+
+#### Basic Usage <!-- {docsify-ignore} -->
+
+Add the MCP server command to your favorite MCP client:
+
+```shell
+flow mcp
+```
+
+The server uses stdio transport and provides AI assistants with:
+
+**Available Tools:**
+- `get_info` - Get flow information, schemas, and current context
+- `execute` - Execute flow workflows
+- `list_workspaces` - List all registered workspaces
+- `get_workspace` - Get details about a specific workspace
+- `switch_workspace` - Change the current workspace
+- `list_executables` - List and filter executables across workspaces
+- `get_executable` - Get detailed information about an executable
+- `get_execution_logs` - Retrieve recent execution logs
+- `sync_executables` - Sync workspace and executable state
+
+**Available Prompts:**
+- `generate_executable` - Generate flow executable configurations
+- `generate_project_executables` - Generate complete project automation sets
+- `debug_executable` - Debug failing executables
+- `migrate_automation` - Convert existing automation to flow
+- `explain_flow` - Explain flow concepts and usage
+
+> [!NOTE]
+> **Learn more about MCP**: Visit the [Model Context Protocol](https://modelcontextprotocol.io) documentation for client setup and integration details.
+
+## CI/CD & Deployment <!-- {docsify-ignore} -->
+
+### GitHub Actions
 
 Execute flow workflows directly in your GitHub Actions pipelines with the official action.
 
@@ -22,7 +63,7 @@ jobs:
 
 > **Complete documentation**: Visit the [Flow Execute Action](https://github.com/marketplace/actions/flow-execute) on GitHub Marketplace.
 
-## Docker
+### Docker
 
 Run flow in containerized environments for CI/CD pipelines or isolated execution.
 

internal/mcp/resources/server-instructions.md

@@ -27,7 +27,7 @@ If the user prompts with any of these concepts, then they are likely referring t
 ## Best Practices
 
 ### Safety
-- **Always confirm** before running `execute_flow` with potentially destructive commands
+- **Always confirm** before running `execute` with potentially destructive commands
 - **Validate YAML** before suggesting users save it to files. The JSON Schemas are provided by the `get_info` tool
 - **Check current context** before making workspace assumptions
 - **Use appropriate filters** when using tools that may return long lists. For instance, provide the appropriate arguments for the `list_executables` tool if you know the target workspace, a keyword, or verb for the executable that you're looking for.
@@ -66,7 +66,7 @@ When tools return JSON, present it in a user-friendly way:
 - **Inspire creativity** - help users see automation opportunities they might not have considered
 
 ## Tool Usage Gotchas
-- `execute_flow` can be used to run flow executables, not arbitrary shell commands or non-exec flow commands.
-  - If an executable has `args` defined, you must provide them in the `args` field of the `execute_flow` tool.
-  - If an executable has `params` defined where the type is `prompt`, you must provide them in the `params` field of the `execute_flow` tool. Do this by providing a mapping of the EnvKey to the value you want to provide.
+- `execute` can be used to run flow executables, not arbitrary shell commands or non-exec flow commands.
+  - If an executable has `args` defined, you must provide them in the `args` field of the `execute` tool.
+  - If an executable has `params` defined where the type is `prompt`, you must provide them in the `params` field of the `execute` tool. Do this by providing a mapping of the EnvKey to the value you want to provide.
 - When running tools, be aware that the current workspace may the output / response. Switch to the workspace that you expect if it's not already set in the context.

internal/mcp/server.go

@@ -2,8 +2,11 @@ package mcp
 
 import (
 	_ "embed"
+	"os"
 
 	"github.com/mark3labs/mcp-go/server"
+
+	"github.com/flowexec/flow/internal/io"
 )
 
 //go:embed resources/server-instructions.md
@@ -29,6 +32,8 @@ func NewServer(executor CommandExecutor) *Server {
 }
 
 func (s *Server) Run() error {
+	_ = os.Setenv(io.DisableInteractiveEnvKey, "true")
+
 	return server.ServeStdio(s.srv)
 }
 

internal/mcp/server_test.go

@@ -84,7 +84,7 @@ var _ = Describe("MCP Server", func() {
 				"switch_workspace",
 				"get_executable",
 				"list_executables",
-				"execute_flow",
+				"execute",
 				"get_execution_logs",
 				"sync_executables",
 			}
@@ -238,14 +238,14 @@ var _ = Describe("MCP Server", func() {
 			})
 		})
 
-		Context("execute_flow tool", func() {
+		Context("execute tool", func() {
 			It("should call executor with provided arguments", func() {
 				expectedOutput := "execution result"
 				mockExecutor.EXPECT().
 					Execute("test", "test:test-flow", "arg1", "arg2").
 					Return(expectedOutput, nil)
 
-				result, err := mcpClient.CallTool(ctx, newCallToolRequest("execute_flow", map[string]interface{}{
+				result, err := mcpClient.CallTool(ctx, newCallToolRequest("execute", map[string]interface{}{
 					"executable_verb": "test",
 					"executable_id":   "test:test-flow",
 					"args":            "arg1 arg2",
@@ -261,7 +261,7 @@ var _ = Describe("MCP Server", func() {
 					Execute("test", "test:test-flow").
 					Return(expectedOutput, nil)
 
-				result, err := mcpClient.CallTool(ctx, newCallToolRequest("execute_flow", map[string]interface{}{
+				result, err := mcpClient.CallTool(ctx, newCallToolRequest("execute", map[string]interface{}{
 					"executable_verb": "test",
 					"executable_id":   "test:test-flow",
 				}))

internal/mcp/tools.go

@@ -116,7 +116,7 @@ func addServerTools(srv *server.MCPServer, executor CommandExecutor) {
 	}
 	srv.AddTool(listExecutables, listExecutablesHandler(executor))
 
-	executeFlow := mcp.NewTool("execute_flow",
+	executeFlow := mcp.NewTool("execute",
 		mcp.WithDescription("Execute a flow executable"),
 		mcp.WithString("executable_verb", mcp.Required(),
 			mcp.Enum(executable.SortedValidVerbs()...),